Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 280 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.2600. Min Act: -0.1696
Data Index: 7691749 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.2270. Min Act: -0.1700
Data Index: 1746279 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1272. Min Act: -0.1700
Data Index: 988112 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1272. Min Act: -0.1700
Data Index: 4442138 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1272. Min Act: -0.1700
Data Index: 5646969 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1439. Min Act: -0.1700
Data Index: 1936434 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1272. Min Act: -0.1699
Data Index: 7691745 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1105. Min Act: -0.1697
Data Index: 470095 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.1105. Min Act: -0.1700
Data Index: 862277 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0937. Min Act: -0.1700
Data Index: 219438 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 3264116 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 5071271 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0602. Min Act: -0.1700
Data Index: 5638754 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1694
Data Index: 7691747 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 6063905 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 6445419 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 110384 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0937. Min Act: -0.1700
Data Index: 6808139 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0770. Min Act: -0.1700
Data Index: 6800639 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2600. Min Range: -2.2600
Max Act: 2.0602. Min Act: -0.1700
Data Index: 5029133 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19